Text Generation
MLX
Safetensors
PyTorch
English
qwen2
nvidia
AceMath
math
CoT
mlx-my-repo
conversational
8-bit precision
Instructions to use tslim1/AceMath-7B-Instruct-mlx-8Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use tslim1/AceMath-7B-Instruct-mlx-8Bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("tslim1/AceMath-7B-Instruct-mlx-8Bit") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use tslim1/AceMath-7B-Instruct-mlx-8Bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "tslim1/AceMath-7B-Instruct-mlx-8Bit"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "tslim1/AceMath-7B-Instruct-mlx-8Bit" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tslim1/AceMath-7B-Instruct-mlx-8Bit", "messages": [ {"role": "user", "content": "Hello"} ] }'
Upload chat_template.jinja with huggingface_hub
Browse files- chat_template.jinja +15 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for message in messages %}
|
| 2 |
+
{%- if message.role == 'user' %}
|
| 3 |
+
{{- '<|im_start|>' + message.role + '
|
| 4 |
+
' + message.content + '
|
| 5 |
+
Please give a step-by-step answer and use a \boxed command to denote the final answer.' + '<|im_end|>' + '
|
| 6 |
+
' }}
|
| 7 |
+
{%- else %}
|
| 8 |
+
{{- '<|im_start|>' + message.role + '
|
| 9 |
+
' + message.content + '<|im_end|>' + '
|
| 10 |
+
' }}{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- if add_generation_prompt %}
|
| 13 |
+
{{- '<|im_start|>assistant
|
| 14 |
+
' }}
|
| 15 |
+
{%- endif %}
|